Vital sign detection method and device based on WiFi channel, medium and electronic equipment

Abstract

The present disclosure provides a WiFi channel-based vital sign detection method, a WiFi channel-based vital sign detection device, a computer readable storage medium and an electronic device, and relates to the technical field of communication. The method comprises the following steps: acquiring channel state information of a WiFi signal propagating in a preset space; the channel state information comprises subcarrier data of a plurality of subcarriers; determining a target subcarrier from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in the frequency domain; filtering the subcarrier data of the target subcarrier using a frequency range of human activity to obtain second filtering data of the target subcarrier; and determining vital sign information of the detected person according to wave crest information of the second filtering data of the target subcarrier in the frequency domain. The present disclosure can accurately perceive the vital sign information of a person through effective processing of the channel state information.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of communication technology, in particular to a WiFi channel based vital sign detection method, a WiFi channel based vital sign detection device, a computer readable storage medium and an electronic device. BACKGROUND

[0002] WiFi (Wireless Fidelity, a wireless network transmission technology) sensing is a technology that uses WiFi signals to detect the presence, location and movement of objects and people in the environment. By analyzing the reflection and attenuation of WiFi signals, WiFi sensing algorithms can determine the location, presence and movement of objects and people, which have wide applications in indoor navigation, smart home automation, health monitoring and security.

[0003] CSI (Channel State Information) as a parameter representing channel changes can sense WiFi data, which is usually collected through a computer network card. Due to the problems of weak received signal, unbalanced terminal device received signal quality, low sampling rate, large environmental interference, large terminal device power consumption, etc., the prior art is difficult to accurately perceive and effectively detect human vital signs on the terminal device side such as mobile phones according to CSI by connecting the terminal device with the router. SUMMARY

[0004] The present disclosure provides a WiFi channel based vital sign detection method, a WiFi channel based vital sign detection device, a computer readable storage medium and an electronic device, thereby at least partially solving the problem that it is difficult to accurately perceive and detect human vital signs according to effective channel state information in the prior art.

[0005] Other characteristics and advantages of the present disclosure will become apparent from the following detailed description, or will be learned by practice of the present disclosure.

[0006] According to a first aspect of the present disclosure, a WiFi channel based vital sign detection method is provided, comprising: acquiring channel state information of a WiFi signal propagating in a preset space; the channel state information comprises subcarrier data of a plurality of subcarriers; determining a target subcarrier from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in the frequency domain; filtering the subcarrier data of the target subcarrier using a frequency range of human activity to obtain second filtering data of the target subcarrier; and determining vital sign information of the detected person according to wave peak information of the second filtering data of the target subcarrier in the frequency domain.

[0007] According to a second aspect of the present disclosure, a WiFi channel based vital sign detection device is provided, comprising: a state information acquisition module configured to acquire channel state information of a WiFi signal propagating in a preset space; the channel state information comprises subcarrier data of a plurality of subcarriers; a target subcarrier determination module configured to determine a target subcarrier from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in a frequency domain; a carrier data filtering module configured to filter the subcarrier data of the target subcarrier using a frequency range of human activity to obtain second filtering data of the target subcarrier; and a vital sign information determination module configured to determine vital sign information of the detected person according to wave peak information of the second filtering data of the target subcarrier in the frequency domain.

[0008] According to a third aspect of the present disclosure, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect and possible implementation manners thereof.

[0009] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory configured to store executable instructions of the processor. The processor is configured to execute the executable instructions to implement the method of the first aspect and possible implementation manners thereof.

[0010] The technical solution of the present disclosure has the following beneficial effects:

[0011] Obtaining channel state information of a WiFi signal propagating in a preset space; the channel state information includes subcarrier data of a plurality of subcarriers; determining a target subcarrier from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in a frequency domain; filtering the subcarrier data of the target subcarrier using a frequency range of human activity to obtain second filtering data of the target subcarrier; and determining vital sign information of a detected person according to peak information of the second filtering data of the target subcarrier in the frequency domain. On the one hand, the example embodiment proposes a new vital sign detection result, which can determine vital sign information of a detected person by processing and analyzing the obtained channel state information, and the detection process does not require the user to wear a contact detection device and does not require the user to perform additional complex operations, that is, the user can achieve a non-invasive detection of the user's vital sign information, the user experience is good, and the application scope is wide. On the other hand, the example embodiment can select appropriate subcarrier data of a target subcarrier for analysis and processing of vital sign information sensing based on the energy values of the subcarrier data of the channel state information in the frequency domain, thereby improving the accuracy and effectiveness of vital sign information determination by effectively processing data. On the other hand, the example embodiment filters the subcarrier data of the target subcarrier using the frequency range of human activity, combines the characteristics of human activity, and can accurately determine effective processing data about human vital signs, thereby saving computing resources and further ensuring the accuracy and efficiency of vital sign information determination.

[0012] It should be understood that the general description above and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0013] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained from these drawings without creative labor for those skilled in the art.

[0014] Figure 1 A schematic diagram showing a system architecture in the example embodiment;

[0015] Figure 2 A flowchart showing a vital sign detection method for a WiFi channel in the example embodiment;

[0016] Figure 3 A sub-flowchart showing a vital sign detection method for a WiFi channel in the example embodiment;

[0017] Figure 4Fig. 2 shows a schematic diagram of carrier data of a human activity of breathing in the present exemplary embodiment;

[0018] Figure 5 Fig. 4 shows a schematic diagram of comparison of data of the present exemplary embodiment and data measured by a conventional wearable device;

[0019] Figure 6 Fig. 5 shows a schematic diagram of an antenna layout in the present exemplary embodiment;

[0020] Figure 7 Fig. 6 shows a schematic diagram of another antenna layout in the present exemplary embodiment;

[0021] Figure 8 (a)- Figure 8 (b) shows a time domain diagram of each subcarrier in the channel state data of different links;

[0022] Figure 9 (a)- Figure 9 (b) shows a time domain diagram of the data of link 1 before and after filtering;

[0023] Figure 10 Fig. 9 shows a frequency domain diagram of the data of link 1;

[0024] Figure 11 (a)- Figure 11 (b) shows a time domain diagram of the data of link 2 before and after filtering;

[0025] Figure 12 Fig. 11 shows a frequency domain diagram of the data of link 2;

[0026] Figure 13 (a)- Figure 13 (c) shows a time domain diagram of the carrier data of the first link;

[0027] Figure 14 Fig. 14 shows a frequency domain diagram of the carrier data of the first link;

[0028] Figure 15 (a)- Figure 15 (c) shows a time domain diagram of the carrier data of the second link;

[0029] Figure 16 Fig. 17 shows a frequency domain diagram of the carrier data of the second link;

[0030] Figure 17 Fig. 18 shows a flow chart of a sleep quality evaluation method in the present exemplary embodiment;

[0031] Figure 18 Fig. 20 shows a module diagram of another vital sign detection method based on WiFi channel in the present exemplary embodiment;

[0032] Figure 19 A flowchart of a process of acquiring channel state information in the present example embodiment is shown.

[0033] Figure 20 A block diagram of a device for detecting vital signs based on a WiFi channel in the present example embodiment is shown.

[0034] Figure 21 A block diagram of an electronic device in the present example embodiment is shown. DETAILED DESCRIPTION

[0035] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, however, can be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the example embodiments to those skilled in the art. The features, structures, or characteristics described in connection with the embodiments can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the aspects of the disclosure can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, materials, or operations are not shown or described in detail in order to avoid obscuring aspects of the disclosure.

[0036] Furthermore, the accompanying drawings are only intended to show illustrative views of the disclosure, and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities, which do not necessarily have to correspond to physically or logically independent entities. The functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0037] Reference Figure 1 As shown, the system architecture 100 can include a gateway device 110, a person 120, and a terminal device 130. The gateway device 110 can be a router or the like hardware device capable of connecting a network or transmitting data information. The terminal device 130 can be a mobile phone, a tablet computer, a smart wearable device, or the like electronic device. The gateway device 110 and the terminal device 130 can be connected through a wired or wireless communication link to perform data interaction. The system architecture 100 covers a WiFi signal. The terminal device 130 can be connected to the gateway device 110 to detect vital signs of the person 120 by acquiring channel state information of the WiFi channel.

[0038] The following will be described in combination with Figure 2 The flow of the vital sign detection method based on the WiFi channel is described. Referring to Figure 2 As shown in the figure, the vital sign detection method based on the WiFi channel can include the following steps S210 to S240:

[0039] Step S210, acquiring channel state information of a WiFi signal propagating in a preset space; the channel state information includes subcarrier data of multiple subcarriers.

[0040] In wireless communication, channel state information CSI is a kind of data for sensing WiFi, which can be used to describe how the signal is transmitted from the transmitting end to the receiving end through the channel. It represents a series of comprehensive influences, such as scattering, fading, and energy attenuation with distance. In the present exemplary embodiment, the WiFi signal can propagate in a preset space, which can be any environment or scene, such as a home or a shopping mall, etc. The WiFi signal propagates in the preset space, which can be considered to be distributed in the preset space, so when a person is active in the scene, it will affect the propagation of the signal, and the WiFi signal will undergo physical phenomena such as scattering on the person's body, which will be recorded by the channel state information. Among them, the transmitting end and the receiving end have diversity according to different application scenarios, for example, in a smart home, the transmitting end can be a router at home, and the receiving end can be a mobile phone, a tablet computer, or various household appliances with WiFi modules, such as a sweeping robot, a smart TV, etc. The present exemplary embodiment can detect the vital signs of a person by acquiring the channel state information of the WiFi channel.

[0041] In the field of wireless communication technology, the carrier is the physical basis for transmitting information and can be used to transmit information. Carrier data refers to data transmitted through a carrier, which can refer to continuous signal data of a pre-defined preset frequency. In the present exemplary embodiment, the channel state information can include subcarrier data of multiple subcarriers.

[0042] Step S220, determining a target subcarrier from the multiple subcarriers based on the energy values of the subcarrier data of the multiple subcarriers in the frequency domain.

[0043] After obtaining the channel state information of the subcarrier data including a plurality of subcarriers, the exemplary embodiment can perform channel state information processing to determine target subcarriers from the plurality of subcarriers, so as to perform subsequent steps by using the subcarrier data of the target subcarriers. Specifically, the target subcarriers can be selected according to the energy values of the subcarrier data of the plurality of subcarriers in the frequency domain. For example, the energy values of the subcarrier data of the plurality of subcarriers are sorted, and one or more subcarriers with the largest energy values are determined as the target subcarriers according to the sorting result, or a preset number of subcarriers are determined as the target subcarriers according to the energy values, for example, the first two or the first three subcarriers sorted from large to small in energy value are selected as the target subcarriers, etc. The energy of the subcarrier data in the frequency domain can be characterized by the power spectral density of the subcarrier data transformed to the frequency domain.

[0044] In step S230, the subcarrier data of the target subcarriers is filtered by using the frequency range of human activity to obtain second filtered data of the target subcarriers.

[0045] Human activity refers to activity reflecting changes in human physical signs, which can generate a series of data, such as breathing data and heartbeat data. The breathing data refers to data determined according to the breathing activity of a person. Breathing is the activity of the respiratory tract and lungs of the human body. Generally, the normal breathing frequency of the human body is 0.2 Hz-0.5 Hz (Hertz). The breathing data can include breathing frequency, breathing rate, etc. The heartbeat data refers to data determined according to the heartbeat activity of a person, for example, it can be heart rate, which is the number of heartbeats per minute in a normal person in a quiet state, also known as quiet heart rate, generally 60-100 times / minute, or 0.8 Hz-2.0 Hz, which can vary individually due to age, gender or other physiological factors. The respiratory data and heartbeat data of a person can be obtained by analyzing the chest fluctuation data in the present exemplary embodiment. The chest fluctuation data can be the fluctuation amplitude of the chest cavity. Generally, the fluctuation amplitude of the chest cavity is 0 cm-3 cm (centimeters) when a healthy adult is in a calm state and breathes, and the fluctuation amplitude of the chest cavity caused by heartbeat is 1.5 mm-3.5 mm (millimeters).

[0046] The present exemplary embodiment can determine the frequency range of human activity based on normal human activity data, and can determine the frequency range of different activity types, for example, for respiratory activity, 0.15-0.8 Hz can be determined as the frequency range of human activity, and the target subcarrier data is filtered; for heartbeat activity, 0.9 Hz-2 Hz can be determined as the frequency range of human activity, and the target subcarrier data is filtered, to determine the second filtered data after filtering, which can include index energy for representing human body state, such as respiratory steady-state energy, etc. The frequency range of human activity can be adjusted or set according to the range of different activity types, which is not specifically limited in the present disclosure.

[0047] In step S240, the vital sign information of the detected person is determined according to the peak information of the target subcarrier in the frequency domain.

[0048] The present exemplary embodiment can transform the second filtered data of the target subcarrier to the frequency domain after determining the second filtered data of the target subcarrier, to obtain the waveform information of the second filtered data, and further determine the vital sign information of the detected person according to the peak information of the target subcarrier in the frequency domain.

[0049] The vital sign information can be a judgment result of normality or abnormality, for example, it can be a result of whether the respiration, heartbeat and other signs are normal, or it can be a detailed analysis result, for example, a respiratory / heart rate report, or a corresponding functional result generated in combination with a scene, for example, a sleep evaluation result generated according to the vital sign information (respiratory / heart rate information) of the user in the sleep time period, etc.

[0050] In addition, the present exemplary embodiment can also send prompt information to the terminal device according to the vital sign information, to inform the user of the sign monitoring result, for example, when the respiration or heart rate appears abnormal, a notification reminder is sent to confirm to the user, or information or notification is sent to the emergency contact of the user, etc.

[0051] In the example embodiment, the channel state information of the WiFi signal propagating in the preset space is obtained, the detected person exists in the preset space, the channel state information includes subcarrier data of a plurality of subcarriers, a target subcarrier is determined from the plurality of subcarriers based on the energy values of the subcarrier data of the plurality of subcarriers in the frequency domain, the subcarrier data of the target subcarrier is filtered using the frequency range of human activity to obtain second filtered data of the target subcarrier, and the vital sign information of the detected person is determined according to the peak information of the second filtered data of the target subcarrier in the frequency domain. On the one hand, the example embodiment proposes a new vital sign detection result, which can determine the vital sign information of the detected person by processing and analyzing the obtained channel state information, and the detection process does not require the user to wear a contact detection device and does not require the user to perform additional complex operations, that is, the user can be detected without feeling, the user experience is good, and the application range is wide. On the other hand, the example embodiment can select appropriate subcarrier data of the target subcarrier for analysis and processing of vital sign information sensing based on the energy values of the subcarrier data of the channel state information in the frequency domain, thereby improving the accuracy and effectiveness of vital sign information determination by effectively processing data. On the other hand, the example embodiment filters the subcarrier data of the target subcarrier using the frequency range of human activity, combines the characteristics of human activity, and accurately determines the effective processing data related to the human sign, thereby saving computing resources and further ensuring the accuracy and efficiency of vital sign information determination.

[0052] In an example embodiment, the above step S220 can include:

[0053] The subcarrier data of the plurality of subcarriers is transformed to the frequency domain, and the energy values of the plurality of subcarriers in the frequency domain are sorted from high to low, and a first preset number of subcarriers with high energy values are selected as target subcarriers.

[0054] In the example embodiment, the subcarrier data of the plurality of subcarriers can be transformed to the frequency domain by performing N-point fast Fourier transform on the subcarrier data, where the value of N can be customized according to actual needs, for example, N can be 256, 512, 1024, etc. Then, the energy values of the plurality of subcarriers in the frequency domain after frequency domain transformation can be sorted from high to low, and a first preset number of subcarriers with high energy values are selected as target subcarriers, where the first preset number can be customized, for example, the first preset number can be set to 1, 2, or 3, etc. In the example embodiment, in order to ensure the accuracy and convenience of data processing, the first preset number can be set to 1, that is, the subcarrier data of the target subcarrier containing the most human respiratory signals can be selected for subsequent processing.

[0055] Further, in an example embodiment, before transforming the subcarrier data of the plurality of subcarriers into the frequency domain, the above-mentioned WiFi channel-based vital sign detection method can further include:

[0056] filtering the subcarrier data of the plurality of subcarriers using a basic frequency range to obtain first filtering data of the plurality of subcarriers;

[0057] The above-mentioned transforming the subcarrier data of the plurality of subcarriers into the frequency domain includes:

[0058] transforming the first filtering data of the plurality of subcarriers into the frequency domain.

[0059] The basic frequency range can be a reference frequency range that can determine or identify human activities in a scene according to a signal, which can be determined according to the normal breathing frequency or normal heartbeat frequency of the human body, and can cover a more suitable range of normal human activities, which can be customized according to actual needs. The basic frequency range can be a range that can determine the range of breathing or heartbeat, such as 0.15-2Hz; or it can be a plurality of ranges corresponding to different human activities, such as a basic frequency range of 0.15-1Hz for breathing activities and a basic frequency range of 0.8-2Hz for heartbeat activities. When the terminal device has multiple links, such as using multiple antennas to collect channel state information, different links can determine different basic frequency ranges for different types of human activities to filter the subcarrier data of the plurality of subcarriers, such as each link can determine a basic frequency range for breathing activities or a basic frequency range for heartbeat activities, and filter through the respective basic frequency ranges. In addition, different links can also determine the same basic frequency range for the same type of human activity, such as multiple links can set the same basic frequency range for breathing activities or the same basic frequency range for heartbeat activities to filter the data of human activities. In addition, a part of the links can be set with a basic frequency range for a first type of human activity, and another part of the links can be set with a basic frequency range for a second type of human activity, so as to filter the data of different types of human activities through different links, such as setting a basic frequency range for heartbeat activities for the first link and setting a basic frequency range for breathing activities for the second link and the third link, so as to filter the data of heartbeat activities through the first link and filter the data of breathing activities through the second link and the third link, and so on. The basic frequency range can be set to be greater than the frequency range of human activities, such as the frequency range of human activities under breathing activities can be set to 0.15Hz-0.8Hz, and the basic frequency range can be set to 0.15Hz-1Hz.

[0060] In an example embodiment, the above-mentioned transforming subcarrier data of a plurality of subcarriers into a frequency domain, and sorting energy values of the plurality of subcarriers in the frequency domain from high to low, and selecting a first preset number of subcarriers with higher energy values as target subcarriers can include:

[0061] transforming subcarrier data of a plurality of subcarriers into a frequency domain to obtain a first power spectral density of each subcarrier in the frequency domain;

[0062] performing normalization processing on the first power spectral density to obtain a normalized first power spectral density;

[0063] sorting the maximum normalized first power spectral density of each subcarrier in descending order, and selecting a first preset number of subcarriers with higher normalized first power spectral density as target subcarriers.

[0064] The power spectral density refers to the energy distribution of a signal in the frequency domain per unit frequency. In the example embodiment, the power spectrum of the signal can be determined based on the Fourier transform result, and the power spectral density can be determined based on the ratio of the power spectrum to the frequency width.

[0065] In the example embodiment, the subcarrier data of the plurality of subcarriers can be transformed into the frequency domain, the first power spectral density of each subcarrier in the frequency domain can be determined by calculation, and then the first power spectral density of each subcarrier can be normalized to obtain the normalized first power spectral density, which is represented as: The basic frequency range of 0.15-1 Hz can be used to filter the subcarriers. Further, the maximum normalized first power spectral density of each subcarrier can be sorted in descending order, and a first preset number of subcarriers with higher normalized first power spectral density can be selected as target subcarriers for subsequent evaluation of human activities such as respiration or heartbeat.

[0066] In the example embodiment, the subcarrier data of the plurality of subcarriers can be filtered using the basic frequency range to obtain first filtered data, and the first filtered data can be transformed into a frequency domain by fast Fourier transform to determine the first power spectral density. According to the sorting result of the normalized first power spectral density from large to small, a first preset number of subcarriers can be selected as target subcarriers. Further, the subcarrier data of the target subcarriers can be filtered using a frequency range of human activities with a smaller range to obtain second filtered data of the target subcarriers, and the vital sign information of the detected person can be determined based on the second filtered data.

[0067] In the example embodiment, after the target subcarriers of different links are determined, the target subcarriers of different links can be sequentially identified and band-pass filtered according to the frequency range of human activities, for example, the target subcarriers of different links can be band-pass filtered according to the frequency range of respiratory activities of human activities, the band-pass filter can be set to 0.15-0.8 Hz, and the filtered data is subjected to fast Fourier transform to obtain second filtered data. Similarly, the target subcarriers of different links can be band-pass filtered according to the frequency range of heartbeat activities of human activities, the band-pass filter can be set to 0.9-2 Hz, and the filtered data is subjected to fast Fourier transform to obtain second filtered data.

[0068] In an example embodiment, as shown in Figure 3 The step S240 can include the following steps.

[0069] In an example embodiment, the step S310 can include the following steps.

[0070] The step S320 can include the following steps.

[0071] After the second filtered data is transformed to the frequency domain, the peak information of the second filtered data in the frequency domain can be determined, and according to the peak information, the human activity frequency and / or the human activity energy value of the detected person can be determined. According to different types of human activities, the human activity frequency is different, for example, the respiratory frequency can be determined for respiratory activities, the heartbeat frequency can be determined for heartbeat activities, etc. The human activity energy value refers to an index value for characterizing human activities by energy, for example, respiratory energy, etc.

[0072] According to the human activity frequency, the human activity energy value, or the human activity frequency and the human activity energy value, the vital sign information of the detected person can be determined, for example, the human activity frequency and / or the human activity energy value in a preset time period are counted, and according to the counting result, the vital sign information of the detected person is determined. Specifically, when the human activity energy value is greater than a preset energy threshold, the vital sign information of the detected person in a motion state is determined, etc.

[0073] In an example embodiment, the step S310 can include the following steps.

[0074] The second filtered data of the target subcarriers is transformed to the frequency domain, and the main peak of the second filtered data in the frequency domain is determined.

[0075] The human activity frequency is determined according to the frequency of the main peak, and / or the human activity energy value is determined according to the energy value of the main peak.

[0076] In order to facilitate data processing, the second filtering data of the target subcarrier can be transformed into the frequency domain, and the main peak in the frequency domain can be determined by peak searching. The main peak can be one or multiple. For example, the main peak can be the peak with the maximum energy value, or 10 peaks can be determined according to the energy value sorting, and 5 peaks with obvious features can be selected from the 10 peaks as the main peak.

[0077] The human activity frequency can be determined based on the frequency of the main peak. Different types of human activities correspond to different main peaks, and different human activity frequencies can be determined. For example, the breathing frequency can be determined according to the main peak of the breathing activity, and the heartbeat frequency can be determined according to the main peak of the heartbeat activity. The human activity frequency can be determined in various ways. For example, the human activity frequency can be determined by weighted calculation according to the frequencies of the main peaks. Alternatively, the frequency corresponding to one of the main peaks can be used as the human activity frequency. Alternatively, the energy value proportion of the main peak with the largest energy value in the peak can be calculated to determine the human activity frequency.

[0078] The human activity energy can be determined within a period of time. For example, the human activity energy value can be determined by frequency statistics of the main peak within a preset time period. The preset time period can be set according to actual needs, for example, the previous N seconds or the previous 2 minutes. The human activity energy can be updated in real time according to the time lapse.

[0079] In an example embodiment, the channel state information of the WiFi signal includes channel state information of the WiFi signal received by multiple links of the terminal device. The second filtering data includes second filtering data corresponding to the multiple links.

[0080] In the example embodiment, the terminal device can receive the channel state information of the WiFi signal through multiple links. The second filtering data can include second filtering data corresponding to the multiple links. The link can be an antenna configured by the terminal device. The channel state information of the WiFi signal is received through different antennas, that is, the channel state information of the WiFi signal is received through multiple links of the terminal device.

[0081] The second filtering data of the target subcarrier is transformed into the frequency domain, and the main peak of the second filtering data in the frequency domain is determined. The method can include the following steps:

[0082] The second filtering data corresponding to each link is transformed into the frequency domain, and the second power spectral density of the target subcarrier in the frequency domain is determined.

[0083] normalizing the second power spectrum density to obtain a normalized second power spectrum density;

[0084] For each link, a peak search is performed on the normalized second power spectrum density in the frequency domain to determine the first preset number of peaks of the normalized second power spectrum density in descending order, and to determine a peak of the normalized second power spectrum density that exceeds a preset energy threshold as a main peak.

[0085] In the present exemplary embodiment, after the second filtered data corresponding to each link is transformed to the frequency domain, the second power spectrum density corresponding to the second filtered data can be determined according to the energy distribution in the frequency domain. In order to facilitate subsequent processing, the second power spectrum density can be normalized to obtain a normalized second power spectrum density. Then, for each link, a peak search can be performed on the normalized second power spectrum density in the frequency domain to determine the first preset number of peaks of the normalized second power spectrum density in descending order. For example, the target subcarrier data of different links is band-pass filtered in the human activity frequency range of respiratory activity and transformed to the frequency domain, and the normalized second power spectrum density in the frequency domain is determined, which has a physical meaning of the signal-to-noise ratio of the respiratory component. A local peak search is performed on the normalized power spectrum density to obtain the first M largest frequency components, where M can be 2-6, which is not specifically limited by the present disclosure. When M is 2-6, it can be used for detection of human respiratory activity in a multi-person scenario. Then, it is determined whether the normalized second power spectrum density exceeds a preset energy threshold SNP resp When the normalized second power spectrum density exceeds the preset energy threshold SNP resp , it can be considered as a usable signal, and the corresponding peak is taken as the main peak.

[0086] Similarly, for heartbeat activity, the target subcarriers of different links are filtered in the heartbeat frequency of the human activity frequency range of heartbeat activity and transformed to the frequency domain, the normalized second power spectrum density in the frequency domain is determined, which has a physical meaning of the signal-to-noise ratio of the heartbeat component. A local peak search is performed on the normalized power spectrum density to obtain the first M largest frequency components, where M can be 2-6, which is not specifically limited by the present disclosure. When M is 2-6, it can be used for detection of human heartbeat activity in a multi-person scenario. Then, it is determined whether the normalized second power spectrum density exceeds a preset energy threshold SNP heart When the normalized second power spectrum density exceeds the preset energy threshold SNP heart , it can be considered as a usable signal, and the corresponding peak is taken as the main peak. The preset energy threshold SNP resp , SNP heart may be customized according to actual needs, which is not specifically limited by the present disclosure.

[0087] Further, in an example embodiment, the determining the human activity frequency according to the frequency of the main peak comprises:

[0088] comparing the normalized second power spectral densities corresponding to the main peaks of each link, and taking the frequency corresponding to the maximum normalized second power spectral density as the human activity frequency.

[0089] For example, after determining the main peak corresponding to the human respiratory activity, the frequency corresponding to the maximum normalized power spectral density can be selected as the final respiratory frequency by comparing the normalized second power spectral densities corresponding to the main peaks of different links; after determining the main peak corresponding to the human heartbeat activity, the frequency corresponding to the maximum normalized power spectral density can be selected as the final heartbeat frequency by comparing the normalized second power spectral densities corresponding to the main peaks of different links, etc.

[0090] Figure 4 A schematic diagram of carrier data of human activity as respiratory activity is shown, wherein curve a represents the respiratory frequency data of respiratory activity in a sleep scenario, and curve b is the maximum normalized second power spectral density. In this example embodiment, a preset energy threshold SNP resp is set to 1, and according to the curve as shown in the figure, only the respiratory rate when the maximum normalized second power spectral density exceeds 1 is a credible available signal, and the corresponding peak can be taken as the main peak, and then the respiratory frequency is determined, etc.

[0091] Figure 5 A comparison between the respiratory data corrected by introducing the normalized power spectral density factor and the data measured by a traditional wearable device is shown. The traditional wearable device can obtain corresponding sensing data by configuring a gyroscope or an accelerometer. It can be seen that the data determined by the example embodiment is consistent with the traditional measurement data, which shows that the human activity data determined by the example embodiment has a high degree of accuracy.

[0092] In an example embodiment, the terminal device includes a plurality of WiFi antennas, each WiFi antenna forming a link; the terminal device has four side edges in addition to the display plane and the opposite plane of the display plane, wherein the first side edge and the third side edge are long edges, and the second side edge and the fourth side edge are short edges, and the second side edge and the fourth side edge are divided into a top edge and a bottom edge.

[0093] If the terminal device includes two WiFi antennas, the two WiFi antennas are respectively distributed on any long edge and the second side edge, and the phase distance between the two WiFi antennas is greater than a preset distance.

[0094] If the terminal device includes three WiFi antennas, among the three WiFi antennas, the first WiFi antenna is arranged at the first side edge, the second WiFi antenna is arranged at the top edge, and the third WiFi antenna is arranged at a position between the middle of the third side edge and the edge close to the fourth side edge.

[0095] Considering the integrated layout architecture of mobile phone WiFi antenna communication and perception, and considering the habits of users using terminal devices, for example, when playing games or watching videos, the terminal device is usually held horizontally, different antenna layouts can be configured for the terminal device. The antenna can be a WiFi 5G (5th Generation Mobile Communication Technology, 5th Generation Mobile Communication Technology) antenna or other.

[0096] Layout one, the terminal device can include two WiFi antennas, that is, a dual-antenna architecture is configured, and the two WiFi antennas are distributed on any long edge, such as the first side edge or the third side edge, and the top edge, such as the second side edge. The phase distance of the two antennas is greater than a preset distance. Among them, the specific distribution position can be set according to actual needs or the hardware configuration condition of the terminal on the side edge, for example, the antenna can be arranged at the middle, the lower middle or the upper middle of the long edge, and the other antenna can also be arranged at the middle, the left middle or the right middle of the edge. The preset distance can refer to the phase distance that can make the two antennas not affect each other, which can be determined according to the preset wavelength distance, such as Figure 6 As shown in the terminal device 600, the first antenna 610 is arranged at the middle of the left long edge, and the second antenna 620 is arranged at the middle of the upper top edge. The distance between the phase centers of the two antennas is greater than 1 / 2 wavelength, and the preset distance can be 30mm, that is, the phase distance of the two WiFi antennas is greater than 30mm.

[0097] Layout two, the terminal device can include three WiFi antennas, and the three WiFi antennas are distributed on the first side edge, the second side edge and the third side edge of the terminal device, for example, the middle of the first side edge, the middle of the second side edge, and the position between the middle of the third side edge and the edge close to the fourth side edge. As shown in Figure 7 As shown in the terminal device 700, the first antenna 710 can be arranged at the middle of the left long edge, the second antenna 720 can be arranged at the middle of the upper top edge, and the third antenna 730 can be arranged at a position between the middle of the right long edge and the edge close to the lower bottom edge.

[0098] By the above antenna layout, on the one hand, the directivity patterns of the WiFi antennas are complementary when configured on the terminal, reducing the influence of the user holding the terminal device; on the other hand, since the two antennas can be arranged on the two sides of the mobile phone, the antenna positions are orthogonal in geometry, and the antenna spacing is greater than 1 / 2 wavelength, that is, through the example embodiment, the problem of single antenna sensing blind spot can be compensated.

[0099] Figure 8 (a) shows a time-domain diagram of each subcarrier in link one, Figure 8 (a) shows a time-domain diagram of each subcarrier in link one, Figure 8 (b) shows a time-domain diagram of each subcarrier in link two. As can be seen, due to the difference in the layout of the antennas on the terminal device, the WiFi signals received by different antennas also have great differences.

[0100] By processing the subcarriers of the above link one through the above step S220, the subcarrier data of the target subcarriers of link one in the time domain as shown in Figure 9 (a) can be obtained. Filtering the data as shown in Figure 9 (b) can obtain the frequency domain diagram of the breathing frequency of link one as shown in Figure 10 By processing the subcarriers of the above link two through the above step S220, the subcarrier data of the target subcarriers of link two in the time domain as shown in Figure 11 (a) can be obtained. Filtering the data as shown in Figure 11 (b) can obtain the frequency domain diagram of the breathing frequency of link two as shown in Figure 12 (b) can obtain the frequency domain diagram of the breathing frequency of link two as shown in

[0101] Based on the above Figures 9 to 12 It can be seen that the data of link two has better periodicity, and the main component of the breathing has a higher proportion, and the corresponding breathing rate is 20bpm. Since the signal-to-noise ratio of the signal received by link one is low, the main component of the breathing is not obvious, reducing the accuracy of the breathing.

[0102] When the terminal device receives signals of high quality through different antennas, the main component of the breathing can be well separated regardless of which link, and the accurate breathing rate can be obtained. Therefore, accurate and effective layout of the antennas of the terminal device can further improve the accuracy and effectiveness of the vital sign information detection.

[0103] As shown in Figure 13 (a) shows a time-domain diagram of each subcarrier in link one, Figure 13 (a) shows a time-domain diagram of each subcarrier in link one,Figure 13 (b) shows a time-domain diagram of target subcarriers in the first link; Figure 13 (c) shows a time-domain diagram of the second filtered data in the first link after filtering; Figure 14 Fig. 7 shows a frequency-domain diagram of the respiration data after frequency-domain transformation of the second filtered data of the first link. As shown in Fig. 7, Figure 15 Figure 15 (a) shows a diagram of subcarrier data of original channel state information of the second link, i.e., a plurality of subcarriers;

[0104] Figure 15 (b) shows a time-domain diagram of target subcarriers in the second link; Figure 15 (c) shows a time-domain diagram of the second filtered data in the second link after filtering; Figure 16 Fig. 8 shows a frequency-domain diagram of the respiration data after frequency-domain transformation of the second filtered data. As shown in Fig. 8, the main component of respiration can be well separated and a more accurate respiration rate can be obtained for both the first link and the second link.

[0105] In an example embodiment, the vital sign information can include activity state information.

[0106] The step S320 can include:

[0107] The human activity energy value in the first preset time during which the human activity frequency is stable is obtained, and a human activity energy reference value is determined according to the human activity energy value in the first preset time.

[0108] The activity state information of the detected person is determined according to the ratio of the real-time human activity energy value to the human activity energy reference value.

[0109] The human activity energy can be energy determined based on human activities such as respiration or heartbeat, and the body state of the detected person can be judged through the human activity energy. In the example embodiment, the human activity energy reference value can be determined by obtaining the human activity energy value in the first preset time during which the human activity frequency is stable. The human activity frequency stability can be determined by whether the respiration of the person is stable, and the respiration stability can be determined by analyzing the fluctuation of the respiration frequency, for example, when the variance of the respiration frequency is less than a preset threshold, the respiration is considered to be stable. The first preset time can be a preset time period set according to actual needs, for example, the last N seconds of human activity can be used as the first preset time, and the human activity energy value can be updated according to the lapse of the first preset time. The human activity energy value in the first preset time can be directly used as the human activity energy reference value, or the human activity energy reference value can be determined after calculation and processing.

[0110] ​Further, the activity state information of the detected person can be determined according to a ratio of the real-time human activity energy value and a human activity energy reference value. For example, a ratio of the real-time breathing energy and an energy reference value of a breathing steady state is determined. When the ratio is greater than a first preset threshold value, it is considered that the user is in a motion state. When the ratio is less than a second preset threshold value, it is considered that the user is in a breathing pause state. The first preset threshold value and the second preset threshold value can be set according to actual conditions, or determined based on machine learning by collecting a large amount of data, or obtained by experience analysis, and the like.

[0111] In an example embodiment, the vital sign information includes sleep quality information.

[0112] The step S320 can include:

[0113] The human activity energy values of the detected person at a plurality of sampling time points during sleep are obtained.

[0114] The sleep quality information of the detected person is determined according to the average value of the human activity energy values at the plurality of sampling time points and the human activity energy value at each sampling time point.

[0115] The sleep period can be considered as a monitoring time period in which the detected person is considered to be in a sleep state, which can be user-defined or determined by the system. For example, the time period between 10 pm and 7 am. During the sleep period, a plurality of sampling time points T can be set, and the human activity energy values at the plurality of sampling time points are obtained. In order to ensure the effectiveness of data processing, invalid data such as 0 values caused by packet loss and the like can be removed after obtaining the monitoring data. Then, the average energy of the human activity energy values at the plurality of sampling time points is calculated. The sleep quality information of the detected person is determined according to the average value of the human activity energy values at the plurality of sampling time points and the human activity energy value at each sampling time point. For example, the ratio of the human activity energy value at each sampling time point and the average value is calculated. The number of values exceeding the ratio threshold value is recorded as Y. The sleep quality evaluation function f(Y, T) during the sleep period is determined based on machine learning or experience analysis, and the sleep quality evaluation value is outputted, so as to analyze the sleep state of the user and perform health evaluation.

[0116] In an example embodiment, after the step S210, the vital sign detection method based on the WiFi channel can further include:

[0117] The subcarrier data of the plurality of subcarriers is preprocessed.

[0118] The step S220 can include:

[0119] The target subcarrier is determined from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in the frequency domain after preprocessing.

[0120] To avoid the influence of signal interference, signal loss and the like on the acquired channel state data, and further affect the accuracy of the determination of vital sign information, the plurality of subcarrier data can be preprocessed in the example embodiment, and the target subcarrier is determined from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in the frequency domain after preprocessing.

[0121] Figure 17 A flow framework schematic diagram of sleep quality evaluation in the example embodiment is shown, which can specifically include: a channel state data reporting module 1710 configured to acquire channel state data; a channel state data processing module 1720 configured to preprocess the channel state data; a human activity data extraction module 1730 configured to extract human activity data, such as human activity frequency or human activity energy value and the like; a vital sign information determination module 1740 configured to determine vital sign information based on the human activity data; and a sleep quality information determination module 1750 configured to evaluate the sleep quality of the detected person.

[0122] Specifically, in an example embodiment, the preprocessing of the subcarrier data of the plurality of subcarriers can include at least one of the following:

[0123] Interpolation is performed on the subcarrier data to reconstruct the lost data packet in the subcarrier data, so as to obtain the subcarrier data containing the lost data packet;

[0124] The zero frequency component is removed from the subcarrier data;

[0125] The abnormal points in the subcarrier data are processed;

[0126] The subcarrier data is denoised.

[0127] The interpolation can be performed in various ways, such as natural neighbor interpolation, nearest neighbor interpolation, or local polynomial interpolation, and the like, which are not limited in the present disclosure. The denoising can also be achieved by setting a filter, such as a Savitzky-Golay filter, a filtering method based on local polynomial least squares fitting in the time domain for smoothing denoising processing.

[0128] One or more of the above preprocessing methods can be selected for data processing in the example embodiment, and when multiple methods are used for preprocessing, the processing order can be set as needed, such as performing linear interpolation, removing zero frequency component, removing abnormal points, and smoothing denoising in sequence.

[0129] In an example embodiment, the interpolation of the subcarrier data to reconstruct the missing data packets can include:

[0130] The missing time stamp is determined according to the time stamps of the received data packets in the subcarrier data, and the missing data packet corresponding to the missing time stamp is reconstructed by interpolation based on the received data packets adjacent to the missing time stamp.

[0131] The collection of channel state data faces a major problem of packet loss in actual environment. For example, in office buildings, shopping centers and residential areas, various signal sources can cause channel interference. Many deployed wireless access points interfere with each other greatly, and the low sampling rate of the mobile terminal causes serious packet loss. In order to solve the problem caused by packet loss, the original two-dimensional complex matrix R(m, n1) of channel state data is reconstructed by linear interpolation to obtain a new two-dimensional complex matrix R(m, n2) of data packets, where m corresponds to the serial number of the subcarrier, n1 is the number of received data packets, and n2 is the number of reconstructed data packets.

[0132] In an example embodiment, the subcarrier data is a two-dimensional array; and the zero frequency component is removed from the subcarrier data, including:

[0133] The average value of the amplitude of each row of the subcarrier data is calculated, and the amplitude of each row is subtracted from the average value of the amplitude to obtain the subcarrier data with the zero frequency component removed.

[0134] The average value of the amplitude of each subcarrier of the linearly interpolated data packet R(m, n2), i.e. each row of the two-dimensional array, is calculated, and each subcarrier is subtracted from the average value to obtain a two-dimensional amplitude matrix RA(m, n2) with the zero frequency component removed.

[0135] In an example embodiment, the processing of the abnormal points in the subcarrier data can include:

[0136] For each data in the subcarrier data, the absolute deviation of the data from the median value of the adjacent two data is calculated, and if the absolute deviation exceeds a preset deviation threshold, the data is replaced by the median value of the adjacent two data.

[0137] The Hampel filter can be used for filtering to remove abnormal points, and the principle is that for each x value of the basic signal, the median value of the window composed of x and m / 2 adjacent points on the left and right is calculated, and then the standard deviation of x with respect to the median value of the window is calculated. If the difference between x and the median value exceeds the predefined MAD number, i.e. the preset deviation threshold, the value is replaced by the median value. In this example embodiment, m=10 can be taken.

[0138] Figure 18 A module diagram of another WiFi channel based vital sign detection method of the present exemplary embodiment is shown, which can specifically include a data acquisition module 1810, a data preprocessing module 1820, a human activity data extraction module 1830, and a vital sign detection module 1840. The data acquisition module 1810 includes a channel data information obtaining unit 1811 and a channel data information analyzing unit 1812; the data preprocessing module 1820 includes a linear interpolation unit 1821, a zero frequency component removing unit 1822, an abnormal point processing unit 1823, and a de-noising unit 1824; the human activity data extraction module 1830 includes a target sub-carrier determining unit 1831, a frequency domain transforming unit 1832, a local peak estimating unit 1833, and an independent component analyzing unit 1834; and the vital sign detection module 1840 includes a steady-state respiratory energy calculating unit 1841 and a real-time energy ratio classifying unit 1842.

[0139] In an embodiment, the above-mentioned obtaining channel state information of WiFi signals propagating in a preset space can include the following steps:

[0140] Initializing the WiFi CSI obtaining tool, establishing a socket for communicating with the wireless driver interface;

[0141] The WiFi CSI obtaining tool obtains channel state information of WiFi signals through the socket;

[0142] The channel state information is read to the framework layer by the callback function registered by the WiFi CSI obtaining tool.

[0143] The WiFi CSI obtaining tool is used to obtain channel state information of WiFi signals from the hardware layer and report to the software layer. Taking the Android system as an example, as shown in FIG. 6, the WiFi CSI obtaining tool is used to obtain channel state information of WiFi signals from the hardware layer and report to the software layer. Figure 19As shown, the WiFi CSI acquisition tool can be configured and triggered by wpa_supplicant instructions. The WiFi CSI acquisition tool is initialized, a socket for communication with a wireless driver interface (such as nl80211) is established, for example, two sockets can be created through Generic Netlink, wherein the first socket is used for the WiFi CSI acquisition tool to control the HAL (Hardware Abstract Layer) layer, for example, a cmd_socket can be used, and the second socket is used for the WiFi CSI acquisition tool to notify events to the upper layer, for example, an event_socket can be used. After initialization is completed, the channel state information of the WiFi signal can be acquired through the socket, for example, based on the poll mechanism of Linux, the main() function is entered to call the socket, for example, the buffer in the socket is read through the event_socket to acquire the channel state information from the wireless driver interface, and the acquired channel state information can be in Hex (hexadecimal) form. The Framework Layer can implement the HIDL (HAL Interface Definition Language) interface after booting, register a callback function into the WiFi CSI acquisition tool, and define a callback list (callbacks_list). In this way, the callback list can be monitored to monitor the channel state information. After the WiFi CSI acquisition tool acquires the channel state information and caches it, the Framework Layer is notified through the HIDL interface, so that the Framework Layer reads the channel state information to the Framework Layer. The Framework Layer can parse the physical quantity according to the Hex byte sequence of the channel state information, for example, subcarrier data is obtained.

[0144] In an example embodiment, the step S210 described above can include:

[0145] In response to the terminal device satisfying a preset condition, the WiFi channel state information sensing function of the terminal device is started;

[0146] In the case where the WiFi channel state information sensing function is started, the channel state information of the WiFi signal propagating in a preset space is acquired.

[0147] To improve the timeliness and accuracy of the terminal device in determining the vital sign information of a person and avoid invalid calculation to increase system power consumption, the example embodiment can set a judgment mechanism to start the WiFi channel state information sensing function of the terminal device when the terminal device meets the preset condition, and acquire the channel state information of the WiFi signal propagating in the preset space when the WiFi channel state information sensing function is started.

[0148] Specifically, in an example embodiment, the preset condition can include at least one of the following:

[0149] starting a preset application program;

[0150] being in a charging state;

[0151] being in a stationary state, the power being greater than a power threshold, and being currently in a preset time range.

[0152] The preset application program can be an application program related to vital sign information determination, or an application program with a demand for predicting vital sign information, for example, when a user opens a related health application program to determine the vital sign information of the user at the current time or in the current time period, or when the user starts a game, a short video, or the like, the WiFi channel state information sensing function of the terminal device can be started for health monitoring of the user.

[0153] Alternatively, the WiFi channel state information sensing function of the terminal device can also be started in an idle state of the terminal device or in an application scenario with low power consumption, for example, the WiFi channel state information sensing function can be started when the terminal device is in a charging state, or the WiFi channel state information sensing function can be started when the terminal device is in a stationary state, the power is greater than a power threshold, and the current time is in a preset time range. The stationary state can be that the pose state of the terminal device does not change or does not change significantly in a preset time period, which can be detected and determined by configuring a gyroscope or an accelerometer in the terminal device. The power threshold and the preset time range can be customized according to the user's needs or intelligently adjusted according to the user's preference in using the terminal device, for example, the WiFi channel state information sensing function can be automatically started when the mobile phone is in a stationary state, the power is greater than 80%, and the current time is between 10:00 PM and 8:00 AM the next morning, to accurately monitor the vital sign information of the user by acquiring the channel state information of the WiFi signal propagating in the preset space.

[0154] The example embodiment of the present disclosure also provides a vital sign detection device based on a WiFi channel. As shown in Figure 20As shown, the WiFi channel-based vital sign detection apparatus 2000 can include: a state information acquisition module 2010, configured to acquire channel state information of a WiFi signal propagating in a preset space; the channel state information includes subcarrier data of a plurality of subcarriers; a target subcarrier determination module 2020, configured to determine a target subcarrier from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in a frequency domain; a carrier data filtering module 2030, configured to filter the subcarrier data of the target subcarrier using a frequency range of human activity to obtain second filtering data of the target subcarrier; and a vital sign information determination module 2040, configured to determine vital sign information of a detected person according to peak information of the second filtering data of the target subcarrier in the frequency domain.

[0155] In an example embodiment, the target subcarrier determination module includes: an energy sorting unit, configured to transform the subcarrier data of the plurality of subcarriers to the frequency domain, and sort energy values of the plurality of subcarriers in the frequency domain from high to low, and select a first preset number of subcarriers with high energy values as the target subcarriers.

[0156] In an example embodiment, the WiFi channel-based vital sign detection apparatus further includes: a first filtering unit, configured to filter the subcarrier data of the plurality of subcarriers using a basic frequency range before transforming the subcarrier data of the plurality of subcarriers to the frequency domain to obtain first filtering data of the plurality of subcarriers; and the energy sorting unit includes: a frequency domain transformation unit, configured to transform the first filtering data of the plurality of subcarriers to the frequency domain.

[0157] In an example embodiment, the energy sorting unit includes: a first power spectral density acquisition subunit, configured to transform the subcarrier data of the plurality of subcarriers to the frequency domain to acquire first power spectral densities of the subcarriers in the frequency domain; a normalization processing subunit, configured to normalize the first power spectral densities to obtain normalized first power spectral densities; and a first sorting unit, configured to sort the maximum normalized first power spectral densities of the subcarriers in descending order, and select a first preset number of subcarriers with high normalized first power spectral densities as the target subcarriers.

[0158] In an example embodiment, the vital sign information determination module includes: a peak information analysis unit, configured to determine a human activity frequency and / or a human activity energy value of the detected person according to the peak information of the second filtering data of the target subcarrier in the frequency domain; and a vital sign information determination unit, configured to determine the vital sign information of the detected person according to the human activity frequency and / or the human activity energy value.

[0159] In an example embodiment, the peak information analysis unit comprises: a main peak determination subunit configured to transform the second filtered data of the target subcarrier to a frequency domain and determine a main peak of the second filtered data in the frequency domain; and an activity data determination subunit configured to determine a human activity frequency according to a frequency of the main peak and / or determine a human activity energy value according to an energy value of the main peak.

[0160] In an example embodiment, the channel state information of the WiFi signal comprises channel state information of the WiFi signal received by a plurality of links of the terminal device; the second filtered data comprises second filtered data corresponding to the plurality of links; the main peak determination subunit comprises: a frequency domain transformation subunit configured to transform the second filtered data corresponding to each link to a frequency domain and determine a second power spectral density of the target subcarrier in the frequency domain; a second power spectral density determination subunit configured to normalize the second power spectral density to obtain a normalized second power spectral density; and a main peak determination subunit configured to, for each link, perform peak value searching on the normalized second power spectral density in the frequency domain, determine a second preset number of peaks of the normalized second power spectral density from high to low, and determine a peak of the normalized second power spectral density that exceeds a preset energy threshold as the main peak.

[0161] In an example embodiment, the activity data determination subunit comprises: a spectral density comparison subunit configured to compare the normalized second power spectral density corresponding to the main peak of each link, and take a frequency corresponding to a maximum normalized second power spectral density as a human activity frequency.

[0162] In an example embodiment, the terminal device comprises a plurality of WiFi antennas, each WiFi antenna forming a link; the terminal device has four side edges in addition to a display plane and an opposite plane of the display plane, wherein a first side edge and a third side edge are long edges, and a second side edge and a fourth side edge are short edges, and the second side edge and the fourth side edge are a top edge and a bottom edge, respectively; if the terminal device comprises two WiFi antennas, the two WiFi antennas are respectively distributed on any long edge and the second side edge, and a phase distance between the two WiFi antennas is greater than a preset distance; if the terminal device comprises three WiFi antennas, among the three WiFi antennas, a first WiFi antenna is arranged on the first side edge, a second WiFi antenna is arranged on the top edge, and a third WiFi antenna is arranged between a middle part of the third side edge and a position close to the fourth side edge.

[0163] In an example embodiment, the vital sign information comprises activity state information; the vital sign information determining unit comprises: a reference value determining subunit configured to obtain a human activity energy value in a first preset time during which a human activity frequency is stable, and determine a human activity energy reference value according to the human activity energy value in the first preset time; and an energy ratio determining subunit configured to determine the activity state information of the detected person according to a ratio of a real-time human activity energy value to the human activity energy reference value.

[0164] In an example embodiment, the vital sign information comprises sleep quality information; the vital sign information determining unit comprises: an energy value obtaining subunit configured to obtain human activity energy values at a plurality of sampling time points during sleep of the detected person; and a sleep information determining subunit configured to determine sleep quality information of the detected person according to an average value of the human activity energy values at the plurality of sampling time points and the human activity energy value at each sampling time point.

[0165] In an example embodiment, the vital sign detection device based on a WiFi channel further comprises: a preprocessing unit configured to preprocess subcarrier data of a plurality of subcarriers after obtaining channel state information of the WiFi channel; and a target subcarrier determining module configured to determine a target subcarrier from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in the frequency domain after preprocessing.

[0166] In an example embodiment, the preprocessing of the subcarrier data of the plurality of subcarriers comprises at least one of: an interpolation unit configured to interpolate the subcarrier data to reconstruct missing data packets in the subcarrier data to obtain subcarrier data containing the missing data packets; a component removing unit configured to remove zero-frequency components from the subcarrier data; an outlier removing unit configured to process outliers in the subcarrier data; and a denoising unit configured to denoise the subcarrier data.

[0167] In an example embodiment, the interpolation unit is configured to determine a missing timestamp according to a timestamp of a received data packet in the subcarrier data, and interpolate based on the received data packet adjacent to the missing timestamp to reconstruct a missing data packet corresponding to the missing timestamp.

[0168] In an example embodiment, the component removing unit is configured to calculate an amplitude average value for each row of the subcarrier data, and subtract the amplitude average value from the amplitude of each row to obtain subcarrier data with zero-frequency components removed.

[0169] In an example embodiment, the outlier removing unit is configured to calculate, for each data in the subcarrier data, an absolute deviation of the data from a median value of adjacent two data, and replace the data with the median value of the adjacent two data if the absolute deviation exceeds a preset deviation threshold.

[0170] In an example embodiment, the state information obtaining module comprises: a socket establishing unit configured to initialize a WiFi CSI obtaining tool and establish a socket for communicating with a wireless driver interface; an information obtaining unit configured to obtain channel state information of a WiFi signal by the WiFi CSI obtaining tool through the socket; and an information reading unit configured to read the channel state information to a framework layer by a callback function registered in the WiFi CSI obtaining tool by the framework layer.

[0171] In an example embodiment, the state information obtaining module comprises: a function starting unit configured to start a WiFi channel state information sensing function of a terminal device in response to the terminal device satisfying a preset condition; and an information obtaining unit configured to obtain channel state information of a WiFi signal propagating in a preset space in a case where the WiFi channel state information sensing function is started.

[0172] In an example embodiment, the preset condition comprises at least one of the following: starting a preset application; being in a charging state; being in a stationary state, having a power greater than a power threshold, and being currently in a preset time range.

[0173] The specific details of the parts of the above apparatus have been described in detail in the method part embodiments, and thus will not be described again.

[0174] The example embodiments of the present disclosure also provide a computer readable storage medium, which can be implemented in the form of a program product, comprising program codes for causing a terminal device to perform the steps according to various example embodiments of the present disclosure described in the above "example method" part of the specification, for example, any one or more steps in the above "example method" part of the specification. The program product can be in the form of a portable compact disc read-only memory (CD-ROM) and comprises program codes, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited to this, and in this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in conjunction with an instruction execution system, apparatus or device. Figure 2 Or Figure 3 The above "example method" part of the specification. The program product can be in the form of a portable compact disc read-only memory (CD-ROM) and comprises program codes, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited to this, and in this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in conjunction with an instruction execution system, apparatus or device.

[0175] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory, read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0176] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0177] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0178] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0179] Exemplary embodiments of this disclosure also provide an electronic device. The electronic device may include a processor and a memory, the memory storing executable instructions for the processor, and the processor configured to execute the aforementioned vital sign detection method based on a WiFi channel by executing the executable instructions.

[0180] The following is based on Figure 21Taking the mobile terminal 2100 as an example, the construction of this electronic device will be described by way of example. Those skilled in the art will understand that, apart from components specifically designed for mobile purposes, Figure 21 The structure can also be applied to fixed types of equipment.

[0181] like Figure 21 As shown, the mobile terminal 2100 may specifically include: a processor 2101, a memory 2102, a bus 2103, a mobile communication module 2104, an antenna 1, a wireless communication module 2105, an antenna 2, a display screen 2106, a camera module 2107, an audio module 2108, a power module 2109, and a sensor module 2110.

[0182] The processor 2101 may include one or more processing units, such as an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor, and / or an NPU (Neural-Network Processing Unit).

[0183] An encoder encodes (compresses) images or videos to reduce data size for easier storage or transmission. A decoder decodes (decompresses) the encoded data to restore the original image or video data. The mobile terminal 2100 can support one or more encoders and decoders, such as image formats like JPEG (Joint Photographic Experts Group), PNG (Portable Network Graphics), and BMP (Bitmap), and video formats like MPEG (Moving Picture Experts Group) 1, MPEG10, H.1063, H.1064, and HEVC (High Efficiency Video Coding).

[0184] The processor 2101 can be connected to the memory 2102 or other components via the bus 2103.

[0185] The memory 2102 can be used to store computer executable program codes, including instructions. The processor 2101 performs various functional applications of the mobile terminal 2100 and data processing by running the instructions stored in the memory 2102. The memory 2102 can also store application data, such as storing image, video, etc. files.

[0186] The communication function of the mobile terminal 2100 can be implemented by the mobile communication module 2104, the antenna 1, the wireless communication module 2105, the antenna 2, the modem processor, and the baseband processor, etc. The antenna 1 and the antenna 2 are used to transmit and receive electromagnetic wave signals. The mobile communication module 2104 can provide mobile communication solutions such as 3G, 4G, 5G, etc. applied on the mobile terminal 2100. The wireless communication module 2105 can provide wireless communication solutions such as wireless local area network, Bluetooth, near field communication, etc. applied on the mobile terminal 2100.

[0187] The display screen 2106 is used to realize the display function, such as displaying user interface, image, video, etc. The camera module 2107 is used to realize the shooting function, such as shooting image, video, etc. The audio module 2108 is used to realize the audio function, such as playing audio, collecting voice, etc. The power module 2109 is used to realize the power management function, such as charging the battery, powering the device, monitoring the battery status, etc. The sensor module 2110 can include one or more sensors, used to realize the corresponding sensing detection function. For example, the sensor module 2110 can include an inertial sensor, which is used to detect the motion pose of the mobile terminal 2100, and output inertial sensing data.

[0188] Those skilled in the art can understand that each aspect of the disclosure can be implemented as a system, a method or a program product. Therefore, each aspect of the disclosure can be embodied as a whole hardware embodiment, a whole software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system" here. Those skilled in the art can easily think of other embodiments of the disclosure after considering the specification and practicing the disclosed application. The disclosure is intended to cover any variations, uses or adaptations of the disclosure that follow the general principles of the disclosure and include common knowledge or conventional technical means in the art that are not disclosed in the disclosure. The specification and embodiments are only considered as exemplary, and the true scope and spirit of the disclosure are indicated by the claims.

[0189] It should be understood that the present disclosure is not limited to the precise structures described above and shown in the drawings and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for vital sign detection based on WiFi channel, characterized in that, The method comprises: acquiring channel state information of a WiFi signal propagating in a preset space; the channel state information comprises subcarrier data of a plurality of subcarriers; determining a target subcarrier from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in a frequency domain; filtering the subcarrier data of the target subcarrier using a frequency range of human activity to obtain second filtering data of the target subcarrier; determining vital sign information of a detected person according to peak information in the frequency domain of the second filtering data of the target subcarrier; the determining of the vital sign information of the detected person according to the peak information in the frequency domain of the second filtering data of the target subcarrier comprises: determining a human activity frequency and a human activity energy value of the detected person according to the peak information in the frequency domain of the second filtering data of the target subcarrier; the human activity energy value is an index value representing human activity by energy; determining the vital sign information of the detected person according to the human activity frequency and the human activity energy value; the determining of the human activity frequency and the human activity energy value of the detected person according to the peak information in the frequency domain of the second filtering data of the target subcarrier comprises: transforming the second filtering data of the target subcarrier to the frequency domain and determining a main peak of the second filtering data in the frequency domain; determining the human activity frequency according to the frequency of the main peak and determining the human activity energy value according to the energy value of the main peak.

2. The method of claim 1, wherein, the determining of the target subcarrier from the plurality of subcarriers based on the energy values of the subcarrier data of the plurality of subcarriers in the frequency domain comprises: transforming the subcarrier data of the plurality of subcarriers to the frequency domain, sorting the energy values of the plurality of subcarriers in the frequency domain from high to low, and selecting a first preset number of subcarriers with high energy values as the target subcarriers.

3. The method of claim 2, wherein, before transforming the subcarrier data of the plurality of subcarriers to the frequency domain, the method further comprises: filtering the subcarrier data of the plurality of subcarriers using a basic frequency range to obtain first filtering data of the plurality of subcarriers; the transforming of the subcarrier data of the plurality of subcarriers to the frequency domain comprises: transforming the first filtering data of the plurality of subcarriers to the frequency domain.

4. The method of claim 2, wherein, the transforming of the subcarrier data of the plurality of subcarriers to the frequency domain and the sorting of the energy values of the plurality of subcarriers in the frequency domain from high to low and the selection of a first preset number of subcarriers with high energy values as the target subcarriers comprise: transforming the subcarrier data of the plurality of subcarriers to the frequency domain to obtain first power spectral densities of the subcarriers in the frequency domain; performing normalization processing on the first power spectral densities to obtain normalized first power spectral densities; sorting the maximum normalized first power spectral densities of the subcarriers in descending order and selecting a first preset number of subcarriers with high normalized first power spectral densities as the target subcarriers.

5. The method of claim 1, wherein, The channel state information of the WiFi signal comprises channel state information of WiFi signals received by multiple links of the terminal device; and the second filtered data comprises second filtered data corresponding to the multiple links. The transforming of the second filtered data of the target subcarrier to the frequency domain and the determination of the main peak of the second filtered data in the frequency domain comprise: transforming the second filtered data corresponding to each link to the frequency domain and determining the second power spectral density of the target subcarrier in the frequency domain; normalizing the second power spectral density to obtain normalized second power spectral density; for each link, performing peak value searching on the normalized second power spectral density in the frequency domain, determining the second preset number of peaks of the normalized second power spectral density in descending order, and determining the peak of the normalized second power spectral density exceeding the preset energy threshold as the main peak.

6. The method of claim 5, wherein, The determination of the human activity frequency according to the frequency of the main peak comprises: comparing the normalized second power spectral density corresponding to the main peak of each link, and taking the frequency corresponding to the maximum normalized second power spectral density as the human activity frequency.

7. The method of claim 5, wherein, The terminal device comprises multiple WiFi antennas, each of which forms a link; the terminal device has four side edges other than the display plane and the opposite plane of the display plane, wherein the first side edge and the third side edge are long edges, and the second side edge and the fourth side edge are short edges, and the second side edge and the fourth side edge are top edge and bottom edge respectively; if the terminal device comprises two WiFi antennas, the two WiFi antennas are respectively distributed on any of the long edges and the second side edge, and the phase distance of the two WiFi antennas is greater than a preset distance; if the terminal device comprises three WiFi antennas, the first WiFi antenna is arranged on the first side edge, the second WiFi antenna is arranged on the top edge, and the third WiFi antenna is arranged between the middle of the third side edge and the position close to the fourth side edge.

8. The method of claim 1, wherein, The vital sign information comprises activity state information; the determination of the vital sign information of the detected person according to the human activity frequency and the human activity energy value comprises: obtaining the human activity energy value in a first preset time during which the human activity frequency is stable, and determining a human activity energy reference value according to the human activity energy value in the first preset time; determining the activity state information of the detected person according to the ratio of the real-time human activity energy value to the human activity energy reference value.

9. The method of claim 1, wherein, The vital sign information comprises sleep quality information; the determination of the vital sign information of the detected person according to the human activity frequency and the human activity energy value comprises: obtaining the human activity energy value of the detected person at multiple sampling time points during sleep; determining the sleep quality information of the detected person according to the average value of the human activity energy values at the multiple sampling time points and the human activity energy value at each sampling time point.

10. The method of claim 1, wherein, After obtaining the channel state information of the WiFi channel, the method further comprises: preprocessing subcarrier data of the plurality of subcarriers; determining a target subcarrier from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in the frequency domain, comprising: determining a target subcarrier from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in the frequency domain after preprocessing.

11. The method of claim 10, wherein, The preprocessing of the subcarrier data of the plurality of subcarriers comprises at least one of: interpolating the subcarrier data to reconstruct missing data packets in the subcarrier data to obtain subcarrier data containing missing data packets; removing zero-frequency components from the subcarrier data; processing outliers in the subcarrier data; denoising the subcarrier data.

12. The method of claim 11, wherein, The interpolation of the subcarrier data to reconstruct missing data packets in the subcarrier data comprises: determining missing time stamps from time stamps of received data packets in the subcarrier data, and interpolating missing data packets corresponding to the missing time stamps based on received data packets adjacent to the missing time stamps.

13. The method of claim 11, wherein, The subcarrier data is a two-dimensional array; and the removal of zero-frequency components from the subcarrier data comprises: calculating an amplitude average value for each row of the subcarrier data, and subtracting the amplitude average value from the amplitude of each row to obtain subcarrier data with zero-frequency components removed.

14. The method of claim 11, wherein, The processing of outliers in the subcarrier data comprises: for each data in the subcarrier data, calculating an absolute deviation of the data from a median value of adjacent two data, and replacing the data with the median value of the adjacent two data if the absolute deviation exceeds a preset deviation threshold.

15. The method of claim 1, wherein, The obtaining of the channel state information of the WiFi signal propagating in the preset space comprises: initializing a WiFi CSI acquisition tool, establishing a socket for communication with a wireless driver interface; acquiring the channel state information of the WiFi signal by the WiFi CSI acquisition tool through the socket; reading the channel state information to a framework layer by a callback function registered in the WiFi CSI acquisition tool by the framework layer.

16. The method of claim 1, wherein, The obtaining of the channel state information of the WiFi signal propagating in the preset space comprises: in response to a terminal device satisfying a preset condition, starting a WiFi channel state information sensing function of the terminal device; under the condition that the WiFi channel state information sensing function is started, obtaining the channel state information of the WiFi signal propagating in the preset space.

17. The method of claim 16, wherein, The preset condition comprises at least one of: starting a preset application program; being in a charging state; being in a stationary state, having a power greater than a power threshold, and being currently in a preset time range.

18. A WiFi channel based vital sign detection apparatus, characterized in that, comprises: a state information acquisition module configured to obtain the channel state information of the WiFi signal propagating in the preset space; the channel state information comprises subcarrier data of a plurality of subcarriers; a target subcarrier determination module configured to determine a target subcarrier from the plurality of subcarriers based on energy values of the subcarrier data of the plurality of subcarriers in the frequency domain. The carrier data filtering module is configured to filter sub-carrier data of the target sub-carrier by using a frequency range of human activity, to obtain second filtering data of the target sub-carrier. The vital sign information determination module is configured to determine vital sign information of the detected person according to wave peak information in a frequency domain of the second filtering data of the target sub-carrier. The determining of the vital sign information of the detected person according to the wave peak information in the frequency domain of the second filtering data of the target sub-carrier is configured to: determine a human activity frequency and a human activity energy value of the detected person according to the wave peak information in the frequency domain of the second filtering data of the target sub-carrier; the human activity energy value refers to an index value for representing human activity in an energy manner; determine the vital sign information of the detected person according to the human activity frequency and the human activity energy value. The determining of the human activity frequency and the human activity energy value of the detected person according to the wave peak information in the frequency domain of the second filtering data of the target sub-carrier is configured to: transform the second filtering data of the target sub-carrier to a frequency domain, and determine a main wave peak of the second filtering data in the frequency domain; determine the human activity frequency according to a frequency of the main wave peak, and determine the human activity energy value according to an energy value of the main wave peak.

19. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1 to 17.

20. An electronic device, comprising: comprise: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to implement the method of any one of claims 1 to 17 by executing the executable instructions.

Images